{"id":"W2952404326","doi":"10.48550/arxiv.1212.0146","title":"Efficient Community Detection in Large Networks using Content and Links","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Jaccard index; Computer science; Data mining; Cosine similarity; False positive paradox; False positives and false negatives; Graph; Link analysis; Similarity (geometry); Cluster analysis; Information retrieval; Theoretical computer science; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005102439,0.0002561922,0.0003714207,0.0002013871,0.0002529591,0.00004250469,0.0002797702,0.0002575842,0.00004904414],"category_scores_gemma":[0.000003219159,0.000308317,0.0001691353,0.0003177756,0.00007320637,0.00004751696,0.001183973,0.001930067,0.00000243288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001832676,"about_ca_system_score_gemma":0.00002518335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003842046,"about_ca_topic_score_gemma":0.0005713039,"domain_scores_codex":[0.9986554,0.0003762438,0.0002096765,0.0003534094,0.00004239751,0.0003628349],"domain_scores_gemma":[0.998937,0.00008741896,0.0002316513,0.0005625269,0.00007499086,0.0001064016],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003572514,0.0003722128,0.2247342,0.0000257142,0.0001513369,0.0000059348,0.0002395137,0.7644135,0.00007746792,0.008306217,0.000005698777,0.001632432],"study_design_scores_gemma":[0.0003570283,0.00001199658,0.01774591,0.0000967959,0.0001733925,3.996242e-7,0.0003854104,0.9780751,0.00006747502,0.002747193,0.00003907863,0.0003001709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6336887,0.00005966496,0.3655987,0.000001985283,0.00007677083,0.0001787432,0.000008502494,0.00004404501,0.0003428273],"genre_scores_gemma":[0.9995935,0.00001324232,0.0001296963,0.00001239126,0.0001498372,0.000001285888,0.00003585637,0.00001964979,0.00004454674],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3659048,"threshold_uncertainty_score":0.9999369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1054689615358689,"score_gpt":0.2158235239983439,"score_spread":0.1103545624624749,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}